[PATCH 10/16] ARM: vexpress: introduce DCSCB support

[Santosh Shilimkar]

On Thursday 10 January 2013 05:50 AM, Nicolas Pitre wrote:
> This adds basic CPU and cluster reset controls on RTSM for the
> A15x4-A7x4 model configuration using the Dual Cluster System
> Configuration Block (DCSCB).
>
> The cache coherency interconnect (CCI) is not handled yet.
>
> Signed-off-by: Nicolas Pitre <nico at linaro.org>
> ---
>   arch/arm/mach-vexpress/Kconfig  |   8 ++
>   arch/arm/mach-vexpress/Makefile |   1 +
>   arch/arm/mach-vexpress/dcscb.c  | 160 ++++++++++++++++++++++++++++++++++++++++
>   3 files changed, 169 insertions(+)
>   create mode 100644 arch/arm/mach-vexpress/dcscb.c
>
> diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
> index 99e63f5f99..e55c02562f 100644
> --- a/arch/arm/mach-vexpress/Kconfig
> +++ b/arch/arm/mach-vexpress/Kconfig
> @@ -53,4 +53,12 @@ config ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA
>   config ARCH_VEXPRESS_CA9X4
>   	bool "Versatile Express Cortex-A9x4 tile"
>
> +config ARCH_VEXPRESS_DCSCB
> +	bool "Dual Cluster System Control Block (DCSCB) support"
> +	depends on BIG_LITTLE
> +	help
> +	  Support for the Dual Cluster System Configuration Block (DCSCB).
> +	  This is needed to provide CPU and cluster power management
> +	  on RTSM.
> +
>   endmenu
> diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile
> index 80b64971fb..2253644054 100644
> --- a/arch/arm/mach-vexpress/Makefile
> +++ b/arch/arm/mach-vexpress/Makefile
> @@ -6,5 +6,6 @@ ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
>
>   obj-y					:= v2m.o reset.o
>   obj-$(CONFIG_ARCH_VEXPRESS_CA9X4)	+= ct-ca9x4.o
> +obj-$(CONFIG_ARCH_VEXPRESS_DCSCB)	+= dcscb.o
>   obj-$(CONFIG_SMP)			+= platsmp.o
>   obj-$(CONFIG_HOTPLUG_CPU)		+= hotplug.o
> diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c
> new file mode 100644
> index 0000000000..cccd943cd4
> --- /dev/null
> +++ b/arch/arm/mach-vexpress/dcscb.c
> @@ -0,0 +1,160 @@
> +/*
> + * arch/arm/mach-vexpress/dcscb.c - Dual Cluster System Control Block
> + *
> + * Created by:	Nicolas Pitre, May 2012
> + * Copyright:	(C) 2012  Linaro Limited
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2 as
> + * published by the Free Software Foundation.
> + */
> +
> +#include <linux/init.h>
> +#include <linux/kernel.h>
> +#include <linux/io.h>
> +#include <linux/spinlock.h>
> +#include <linux/errno.h>
> +#include <linux/vexpress.h>
> +
> +#include <asm/bL_entry.h>
> +#include <asm/proc-fns.h>
> +#include <asm/cacheflush.h>
> +
> +
> +#define DCSCB_PHYS_BASE	0x60000000
> +
> +#define RST_HOLD0	0x0
> +#define RST_HOLD1	0x4
> +#define SYS_SWRESET	0x8
> +#define RST_STAT0	0xc
> +#define RST_STAT1	0x10
> +#define EAG_CFG_R	0x20
> +#define EAG_CFG_W	0x24
> +#define KFC_CFG_R	0x28
> +#define KFC_CFG_W	0x2c
> +#define DCS_CFG_R	0x30
> +
> +/*
> + * We can't use regular spinlocks. In the switcher case, it is possible
> + * for an outbound CPU to call power_down() after its inbound counterpart
> + * is already live using the same logical CPU number which trips lockdep
> + * debugging.
> + */
> +static arch_spinlock_t dcscb_lock = __ARCH_SPIN_LOCK_UNLOCKED;
> +
> +static void __iomem *dcscb_base;
> +
> +static int dcscb_power_up(unsigned int cpu, unsigned int cluster)
> +{
> +	unsigned int rst_hold, cpumask = (1 << cpu);
> +
> +	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
> +	if (cpu >= 4 || cluster >= 2)
> +		return -EINVAL;
> +
> +	/*
> +	 * Since this is called with IRQs enabled, and no arch_spin_lock_irq
> +	 * variant exists, we need to disable IRQs manually here.
> +	 */
> +	local_irq_disable();
> +	arch_spin_lock(&dcscb_lock);
> +
> +	rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
> +	if (rst_hold & (1 << 8)) {
> +		/* remove cluster reset and add individual CPU's reset */
> +		rst_hold &= ~(1 << 8);
> +		rst_hold |= 0xf;
> +	}
> +	rst_hold &= ~(cpumask | (cpumask << 4));
> +	writel(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
> +
> +	arch_spin_unlock(&dcscb_lock);
> +	local_irq_enable();
> +
> +	return 0;
> +}
> +
> +static void dcscb_power_down(void)
> +{
> +	unsigned int mpidr, cpu, cluster, rst_hold, cpumask, last_man;
> +
> +	asm ("mrc p15, 0, %0, c0, c0, 5" : "=r" (mpidr));
> +	cpu = mpidr & 0xff;
> +	cluster = (mpidr >> 8) & 0xff;
> +	cpumask = (1 << cpu);
> +
> +	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
> +	BUG_ON(cpu >= 4 || cluster >= 2);
> +
> +	arch_spin_lock(&dcscb_lock);
> +	rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
> +	rst_hold |= cpumask;
> +	if (((rst_hold | (rst_hold >> 4)) & 0xf) == 0xf)
> +		rst_hold |= (1 << 8);
> +	writel(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
> +	arch_spin_unlock(&dcscb_lock);
> +	last_man = (rst_hold & (1 << 8));
> +
> +	/*
> +	 * Now let's clean our L1 cache and shut ourself down.
> +	 * If we're the last CPU in this cluster then clean L2 too.
> +	 */
> +
Do you wanted to have C bit clear code here ?
> +	/*
> +	 * A15/A7 can hit in the cache with SCTLR.C=0, so we don't need
> +	 * a preliminary flush here for those CPUs.  At least, that's
> +	 * the theory -- without the extra flush, Linux explodes on
> +	 * RTSM (maybe not needed anymore, to be investigated)..
> +	 */
> +	flush_cache_louis();
> +	cpu_proc_fin();
> +
> +	if (!last_man) {
> +		flush_cache_louis();
> +	} else {
> +		flush_cache_all();
> +		outer_flush_all();
> +	}
> +
> +	/* Disable local coherency by clearing the ACTLR "SMP" bit: */
> +	asm volatile (
> +		"mrc	p15, 0, ip, c1, c0, 1 \n\t"
> +		"bic	ip, ip, #(1 << 6) @ clear SMP bit \n\t"
> +		"mcr	p15, 0, ip, c1, c0, 1"
> +		: : : "ip" );
> +
> +	/* Now we are prepared for power-down, do it: */
You need dsb here, right ?
> +	wfi();
> +
> +	/* Not dead at this point?  Let our caller cope. */
> +}
> +

Regards
Santosh